Commit Graph

55 Commits

Author SHA1 Message Date
William Jeynes 80bc151379 add majority voting 2026-03-24 16:50:41 +00:00
William Jeynes 5ce64290ce Make an ensemble model to combine scores together (very high accuracy) 2026-03-24 15:50:41 +00:00
William Jeynes 87fccb7e2b Add downloading from hugging face 2026-03-24 13:23:08 +00:00
William Jeynes 8c1e35f66f Increase dropout on regression model to cut down on overfitting 2026-03-24 13:16:18 +00:00
William Jeynes 44395bb251 add linear regression model initial version 2026-03-24 12:25:15 +00:00
William Jeynes e368c50577 Add training scripts for distilled, flan. Add run service for flan 2026-03-23 22:43:59 +00:00
William Jeynes c69730df6b Refine scoring to allow for better iteration on frontend. Update generate_adversarial.py 2026-03-22 16:04:38 +00:00
William Jeynes f4e84af272 Make the model less overfitting. Make it harder for an event to be classed as "perfect" 2026-03-18 01:05:24 +00:00
William Jeynes 886b9a7d5d Ensire works on CUDA for extra speed 2026-03-17 23:14:50 +00:00
William Jeynes 8052d5c7ba Working on making the classifier harsher on unseen data 2026-03-17 22:19:03 +00:00
William Jeynes b08c1ada70 Small changes for the next set of human ranking 2026-03-17 00:18:32 +00:00
William Jeynes c89c7054fe Update agent to support new verification style. Update frontend to support new file format and remove redundant logic from old experiments. 2026-03-16 17:16:58 +00:00
William Jeynes 0a7bb114d2 Add removing of duplicates from pipeline. Add to sort step. Move score logic to robertaMetrics node. 2026-03-13 14:51:14 +00:00
William Jeynes d5c6cb444d Add better scoring, ignoring duplicates, catching under and over confidence. Showing difference between "FINE" and "PERFECT" 2026-03-13 12:18:52 +00:00
William Jeynes 8311556855 Add ROBERTA classifier ranking PoC, with 77pc off the bat 2026-03-13 11:24:51 +00:00
William Jeynes f09e36e740 Add initial version of ROBERTA classifier, add ability for multi pi charts 2026-03-11 22:02:31 +00:00
William Jeynes ef6330ec07 Add re-ranker mode to support re-ranking experiments, hopefully we can reduce the loss 2026-03-06 17:27:09 +00:00
William Jeynes f14d112017 Add difference between auto scoring system and our own labels 2026-03-03 15:58:39 +00:00
William Jeynes 6ae551a93f Ensure date is passed to pipeline. Fix woring 2026-03-02 14:58:26 +00:00
William Jeynes c94812ed80 Prepare for mass data collection. Reduce concurrency as to not overwhelm scraper on long sessions. Remode duplicates from fetch script. Removing naming wierdness on scorer frontend. 2026-02-27 14:41:10 +00:00
William Jeynes 201176e71c Refactor scorer for future maintainabiliy 2026-02-26 10:25:49 +00:00
William Jeynes 6c3aa7343d Update how scoring works with two passes of the data for timesaving. Add section on edge case handling to rules. 2026-02-26 10:09:36 +00:00
William Jeynes 8317fd85df Add file logging for errors. Add exponential backoff retry to web search. On failed web search, do not crash pipeline, return placeholder text to loanguage model 2026-02-24 13:05:35 +00:00
William Jeynes 3d0cacd24e Redo rules a little bit. Update fetch to retreive only from some sources. Add statistics to display, fix rules display 2026-02-23 21:56:27 +00:00
William Jeynes cca3c42f5b Fix longstnading bug in wrapper. Add handling to allow for duplicate events to be handelled. Remove analysis script (will replace with more indepth work in main frontend) 2026-02-22 23:12:14 +00:00
William Jeynes 4d92f14527 Getting hits on the block list IMMEDIATLEY. Log to file, might be important later 2026-02-22 15:42:27 +00:00
William Jeynes 2f33338007 Do not enter existing data if it has no good trigger events 2026-02-22 15:29:48 +00:00
William Jeynes d1ab938c0b Add filtering from known disinformation sources 2026-02-22 15:14:58 +00:00
William Jeynes 8ffe8dec82 Use cleaned trigger events in input.jsonl 2026-02-19 12:23:38 +00:00
William Jeynes 5efce05821 Update REAME to include description of data files 2026-02-19 11:43:25 +00:00
William Jeynes 78a49e2843 Start writing cleaned jsonl output. Re-add sentence to trigger prompt. Fix recursion limit 2026-02-19 11:36:31 +00:00
William Jeynes 6f20ade780 Make open webpage more appealing 2026-02-19 10:07:39 +00:00
William Jeynes b70b75bf28 Update readme. add human score calculation changes 2026-02-18 21:05:01 +00:00
William Jeynes dee9973c2a More work on scorer 2026-02-18 20:44:14 +00:00
William Jeynes a2cb93b44e Start refining scorer. Filter data passed to trigger event agent 2026-02-18 15:03:13 +00:00
William Jeynes 3f14b61cd4 Move all data to own folder. Add run shell script. Experiment (unsuccessfully so far) with example retreival 2026-02-16 22:42:13 +00:00
William Jeynes 90894b2c10 Add some preliminary analysis 2026-02-16 14:42:47 +00:00
William Jeynes 6d478fe7ec Add multi claim runner. Add dbkf fetcher for automated testing. Add visualisation tool plus human score enterer. 2026-02-13 15:15:01 +00:00
William Jeynes fa6e7017b0 Add run scripts 2026-02-12 23:52:15 +00:00
William Jeynes 7fe63d6a98 Refactor calculating score. Add sort node for vanity 2026-02-12 23:46:00 +00:00
William Jeynes b06c08daab Add relation model. Add calculate score initial version 2026-02-12 23:26:59 +00:00
William Jeynes c89f73e138 Implement RAGAS metrics 2026-02-12 22:52:22 +00:00
William Jeynes 6dd6bf7eaf implement verification model 2026-02-12 22:32:24 +00:00
William Jeynes bef856d53a Refactor example retreiving, add option for dynamic data. Add hybrid reranking to tooling. Add parsing and loop infrastructure for trigger event processing 2026-02-12 14:33:12 +00:00
William Jeynes 06a302ec36 remove .keep 2026-02-09 21:46:28 +00:00
William Jeynes adccbd5740 cleanup requirements.txt for ragas service 2026-02-09 21:45:56 +00:00
William Jeynes eba5eb40a2 Add RAGAS initial version 2026-02-09 21:26:54 +00:00
William Jeynes cd2c8621e8 FEAT: implement temp version of main tooling feedback loop 2026-02-09 20:25:36 +00:00
William Jeynes 5841e8a922 add search query 2026-02-09 16:45:17 +00:00
William Jeynes 02eac0f553 Allow multiple source CSV files for normalisation. Implement real model node. Add normalizarion prompt. Implement normalization setup. Start on RAG retreival functions 2026-02-09 16:32:40 +00:00